检索结果-内蒙古大学图书馆

2022 Chinese automation Congress, CAC 2022

作者： Xiao, Zhigao Chen, Luefeng Lu, Chengda Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan China University of Alberta Department of Electrical and Computer Engineering Edmonton Canada Tokyo Institute of Technology Yokohama Japan

ISBN: (纸本)9781665465335

In the process of underground drilling in coal mine, there are some cases of drilling resistance but not stuck pipe. The method of data training model to predict stuck drilling will often lead to a high false alarm rate and reduce the prediction accuracy. Therefore, this paper proposes an improved adaptive nero-fuzzy inference system prediction method based on feature analysis (ANFIS-FA). The rotational speed with the strongest correlation was selected as the feature analysis object through principal component analysis, and then the sliding window was used to extract the amplitude change to construct the penalty factor, so as to improve the prediction results of ANFIS. In this paper, the actual drilling data are used for experiments. The results show that ANFIS-FA reduces the false alarm rate and improves the prediction accuracy, which has certain guiding significance for practical drilling. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Facial 3D Regional Structural Motion Representation Using Lightweight Point Cloud Networks for Micro-Expression Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Zhang, Ren Yin, Jianqin Qi, Chao Dang, Yonghao Wang, Zehao Zhang, Zhicheng Liu, Huaping Beijing University of Posts and Telecommunications School of Intelligent Engineering and Automation Beijing100876 China Tsinghua University Department of Computer Science and Technology BNRist Beijing100084 China

Human-computer interaction (HCI) relies on understanding and adapting to users' emotional states. Micro-expressions (MEs), a critical component of emotional perception, are characterized by their spontaneity, rapidity, subtlety, and difficulty to control. They often reveal an individual's true emotions. A comprehensive and detailed representation of motion is necessary to capture the nuances of facial dynamics effectively. Presently, motion representation methods are predominantly confined to 2D analysis within RGB images, overlooking the critical role of facial structure and its movements in conveying emotions. To overcome this limitation, we introduce an innovative facial motion representation that encompasses 3D facial structure, regionalized RGB and structural motion features. Furthermore, we segment the face into eight distinct regions, selecting only the most significant motion points to delineate the primary motion characteristics of each area. To model the interactions among crucial facial motion regions, we employ an advanced, lightweight point cloud and graph convolution network (Lite-Point-GCN). Comprehensive testing on the CAS(ME)3 dataset, using leave-one-subject-out (LOSO), demonstrates that our method outperforms existing state-of-the-art methods. © 2010-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

Scalable Learned Model Soup on a Single GPU: An Efficient Subspace Training Strategy

arXiv

引用

arXiv 2024年

作者： Li, Tao Jiang, Weisen Liu, Fanghui Huang, Xiaolin Kwok, James T. Department of Automation Shanghai Jiao Tong University China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Computer Science University of Warwick United Kingdom

Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups" [45] via exploring various hyperparameter configurations. The Learned-Soup, a variant of model soups, significantly improves the performance but suffers from substantial memory and time costs due to the requirements of (i) having to load all fine-tuned models simultaneously, and (ii) a large computational graph encompassing all fine-tuned models. In this paper, we propose Memory Efficient Hyperplane Learned Soup (MEHL-Soup) to tackle this issue by formulating the learned soup as a hyperplane optimization problem and introducing block coordinate gradient descent to learn the mixing coefficients. At each iteration, MEHL-Soup only needs to load a few fine-tuned models and build a computational graph with one combined model. We further extend MEHL-Soup to MEHL-Soup+ in a layer-wise manner. Experimental results on various ViT models and data sets show that MEHL-Soup(+) outperforms Learned-Soup(+) in terms of test accuracy, and also reduces memory usage by more than 13×. Moreover, MEHL-Soup(+) can be run on a single GPU and achieves 9× speed up in soup construction compared with the Learned-Soup. The code is released at https://***/nblt/MEHL-Soup. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Cryptography Security of Message Communication by Modified Secure IDEA Algorithm 4th

Enhancing the Cryptography Security of Message Communicati...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Haldar, Bilas Sinha, Rohit Paul, Pranam Jha, Prabin Kumar Department of Computer Science and Engineering The Neotia University Diamond Harbour Road South 24 Parganas West Bengal Sarisha743368 India DCG Datacore Systems Pvt. Ltd. Plot 4 DG Block Sector II Kolkata700091 India Department of Computer Science and Engineering Brainware University 398 Ramkrishnapur Road West Bengal Barasat700125 India Department of Robotics and Automation The Neotia University Diamond Harbour Road South 24 Parganas West Bengal Sarisha743368 India

ISBN: (纸本)9789819726134

The security of data has become a top priority in today’s world. An insecure communication network makes data transmission even more challenging. Cryptography can be an effective tool to secure information and ensure the security and confidentiality of information. In cryptography encryption and decryption methods determine communication security, with key sharing. The main purpose of key exchange methods is to provide protection for technology and are not dependent on communication channel security. Encryption and decryption methods determine the transaction security with key sharing. The present work is a new method for generating keys for multi-party communications using a quasi-group approach. A methodology for generating a master key from an unordered value gap was proposed in this work using a quasi-group of order n. The algorithms to generate and renew multiple subkeys from the master key and vice versa are proposed. Additionally, the proposed methods are based on a Modified Secure IDEA (MS-IDEA) algorithm for encryption and decryption using a 256-bit key. The results showed that these methods improve the performance and protection against attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

FRCD: Future Ready Career-Duck a Machine Learning-Driven Career Guidance for Students

FRCD: Future Ready Career-Duck a Machine Learning-Driven Car...

引用

Silchar Subsection Conference (SILCON), IEEE

作者： Priyanshu Paritosh Vedant Yadav Dev Gupta Ujjwal Biswas Department of Mechatronics and Automation Engineering Indian Institute of Information Technology Bhagalpur Bhagalpur India Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bhagalpur India

ISBN: (数字)9798331540821

ISBN: (纸本)9798331540838

In today's society, finding a suitable career is crucial. High school students frequently need to fully understand the notion of labor due to a lack of experience and practical knowledge in various disciplines. This renders students particularly vulnerable to external influences while deciding on a career path. As a result, students must carefully consider high-paying careers to ensure that they align with their interests and skills. Otherwise, students may end up in jobs they dislike or are not suited to. In response to this issue, we intend to develop a machine-learning framework capable of predicting career pathways. Students will receive career recommendation from our model based on their performance and potential. Students can confidently follow their chosen fields if they do well academically; if not, they can choose to change to other fields that better suit them. There are challenges in determining the metrics and improving prediction accuracy to quantify students' career paths and performance in teaching-learning. Best on the test results, the proposed model has a higher prediction accuracy. Also, this method is both reliable and portable, and it may be used to predict career paths in real time.

关键词： Measurement Accuracy engineering profession Education Machine learning Predictive models Real-time systems Planning Reliability Usability

来源：评论

学校读者我要写书评

暂无评论

Generative AI-aided Reinforcement Learning for Computation Offloading and Privacy Protection in VR-based Multi-Access Edge Computing 10

Generative AI-aided Reinforcement Learning for Computation O...

引用

10th IEEE Smart World Congress, SWC 2024

作者： You, Feiran Du, Hongyang Kang, Jiawen Ni, Wei Niyato, Dusit Jamalipour, Abbas The University of Sydney School of Electrical and Computer Engineering SydneyNSW2006 Australia SydneyNSW2122 Australia University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Guangdong University of Technology School of Automation China Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798331520861

The rapid growth of Artificial Intelligence-Generated Content (AIGC) services has led to increased mobile user participation in related computations and interactions. This development has enabled AI-generated characters to interact with Virtual Reality (VR) users in real time, making the VR experience more interactive and personalized. In this paper, we consider an MEC system where VR users engage in AIGC services, focusing on the Generative Diffusion Model (GDM)based image generation tasks. Specifically, VR users initiate requests for computing resources, while computation offloading distributes the processing load across the MEC system. To manage AIGC edge computation offloading and cloudlet-VR user connections jointly, a Data Center Operator (DCO) employs a centralized Proximal Policy Optimization (PPO) algorithm. To protect VR users' privacy while preserving PPO functionality, we employ the Generative Diffusion Model (GDM), specifically the Denoising Diffusion Implicit Model (DDIM), which first introduces noise to the PPO state, then conducts a denoising process to recover the state information. We further employ Inverse Reinforcement Learning (IRL) to infer rewards for the recovered states, using expert demonstrations trained by the PPO. The similarity between PPO-generated rewards and IRL-inferred rewards is then computed. Simulation results demonstrate that our proposed approach successfully achieves computation offloading while protecting VR users' privacy within the PPO centralized management framework. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Development of a prototype of an intelligent system for predicting the quality of dairy manufacture 11

Development of a prototype of an intelligent system for pred...

引用

11th IEEE International Conference on Intelligent Systems, IS 2022

作者： Smitiukh, Yaroslav Samoilenko, Yuliia Kostiuk, Yuliia Kryvoruchko, Olena Stepashkina, Kateryna National University of Food Technologies Department of Automation and Computer Technologies of Control Systems Kyiv Ukraine State University of Trade and Economics Department of Software Engineering and Cyber Security Kyiv Ukraine

ISBN: (纸本)9781665456562

The technological process of the churning process in continuous butter manufacture were considered. The qualitative indicator of the water content of butter was modeled on the basis of a set of industrial data using an artificial neural network (ANN). The prototype of an intelligent system for predicting of the water content of butter allows to increase the information support of the operator-technologist. The proposed model predicts the water content of butter with an error of less than 2%. The input variables of the forecast model prototype are cream fat content, cream ripening temperature, cream supply temperature, frequency of revolutions of the stirrer of the whipping device, and consumption of the normalizing component. Further research is aimed at the development of a decision support information system for dairy manufacture and should be integrated into the subsystem of automated control of the technological process to ensure proper functioning in real time. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Robust Attitude Stabilization of Quadrotor Subject to Stealthy Actuator Attacks 5

Robust Attitude Stabilization of Quadrotor Subject to Stealt...

引用

5th International Conference on Control, Robotics and Informatics, ICCRI 2022

作者： Rebai, Souad Bezzaoucha EIGSI-La Rochelle Department of ElectricalComputer Engineering and Automation 26 Rue François de Vaux de Foletier La Rochelle17041 France

ISBN: (数字)9781665468008

ISBN: (纸本)9781665468008

This publication deals with the robust attitude stabilization of a quadrotor subject to stealthy actuator attacks. Based first on the nonlinear model of the system, the sector non-linearity approach will be applied in order to deduce a polytopic Takagi-sugeno model. In parallel, a polytopic fuzzy T-S modeling of the data-deception malicious attacks (time-varying parameters) is presented. After some mathematical development, it will be shown that our original nonlinear system subject to stealthy actuator attacks can be represented as an uncertain polytopic T-S system. Based on this latest model, basic concepts for attitude stabilization will be used to implement the control law. The stabilization conditions will be given in terms of Linear Matrix Inequalities (LMIs) deduced from a classical Lyapunov approach. In order to highlight the efficiency of the proposed approach, simulation results will be given. © 2022 IEEE.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

High-Performance GPU based Planetary-Scale Terrain Visualization 2022

High-Performance GPU based Planetary-Scale Terrain Visualiza...

引用

5th International Conference on Image and Graphics Processing, ICIGP 2022

作者： Masood, Zafar Zheng, Jiangbin Ahmad, Idrees Irfan, Muhammad Saeed, Amir School of Software Northwestern Polytechnical University Xi’an China Department of Computer Science and Software Engineering International Islamic University Islamabad Pakistan School of Automation and Electrical Engineering Beihang University China

ISBN: (纸本)9781450395465

High-performance visualization of planetary-scale multi-resolution terrain for high-fidelity display systems is a challenging task. Real-world terrain visualization requires real-time modeling and rendering of the large-scale multi-resolution model. This work proposes a novel method for high-performance multi-resolution terrain modeling and rendering using hardware tessellation. The proposed method submits patch primitives using geometry instancing for high-performance. Patch Level-of-detail (LOD) is simplified using a view-dependent simplification algorithm with error control. The proposed simplification algorithm simplifies the model using viewer information and local height variation for optimum triangulation. Patch simplified LOD is tessellated utilizing a fixed-function tessellator. Height grid-aligned post-tessellated vertices are displaced in 3D to construct accurate high-frequency surface details. Finally, multi-resolution satellite imagery and normal maps are utilized for real-world features display. We evaluated the proposed method for high display resolutions and achieved high rendering rate. The proposed method results are compared with clipmap-based and hardware tessellation based methods. © 2022 ACM.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation of Solar Cells via Weighted Mean of Vectors Algorithm

Parameter Estimation of Solar Cells via Weighted Mean of Vec...

引用

2022 IEEE Global Energy Conference, GEC 2022

作者： Izci, Davut Ekinci, Serdar Dal, Suleyman Sezgin, Necmettin Batman University Department of Electronics and Automation Batman Turkey Batman University Department of Computer Engineering Batman Turkey Rectorate Batman University Distance Learning Research Center Batman Turkey

ISBN: (数字)9781665497510

ISBN: (纸本)9781665497510

The renewable energy sources has seen an intense attraction from the research community due to their undeniable potential in terms of sustainability. Amongst them, the solar energy holds a unique place because of the global availability. However, certain challenges must be addressed to appropriately integrate the photovoltaic cells with the power networks. In this regard, this paper investigates the promise of a new intelligent optimization technique named weighted mean of vectors (also known as INFO) algorithm in terms of successfully estimating the parameters of single and double diode photovoltaic models. The obtained results are compared with that of the available approaches reported in literature. The proposed optimization technique is demonstrated to have good performance for successfully estimating the parameters of single and double diode models of the photovoltaic cells. © 2022 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：